AB ten-defeats
Use when Codex is asked to plan, design, implement, modify, refactor, debug, test, review, verify, or complete non-trivial software work; use Computer Use or operate a browser, desktop UI, or live app; coordinate multiple tools; or delegate to agents. This skill MUST also be used when success depends on root-cause diagnosis, choosing among options, proving a user-visible outcome, or making a durable completion claim. Do not use for simple facts, translation, or trivial text-only edits.
use Computer Use or operate a browser, desktop UI, or live app; coordinate multiple tools; or delegate to agents.
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 974 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 490: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 24 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.